mlsanityData to 7 Oct 2026

Interventional Few-Shot Learning

arXiv 2009.13000 ↗First posted 28 Sep 2020cs.LG cs.CVcited by 112

Not on the map. Why?

Abstract (arXiv)

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on textitminiImageNet, textittieredImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 19; 2023: 33; 2024: 15; 2025: 7; 2026: 3.

112 papers.

Sort:

By area:

  1. 2021GPT Understands, Toocited by 715
  2. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  3. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  4. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  5. 2021Causal Attention for Vision-Language Taskscited by 111
  6. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  7. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  8. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  9. 2021Deconfounded Video Moment Retrieval with Causal Interventioncited by 84
  10. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  11. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  12. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
38 more
  1. 2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
  2. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  3. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  4. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  5. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  6. 2023Backdoor Defense via Deconfounded Representation Learningcited by 38
  7. 2023GaitGCI: Generative Counterfactual Intervention for Gait Recognitioncited by 30
  8. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  9. 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
  10. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  11. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  12. 2022Causal Transportability for Visual Recognitioncited by 23
  13. 2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 23
  14. 2021Learning Domain Invariant Representations for Generalizable Person Re-Identificationcited by 22
  15. 2021Uncovering Main Causalities for Long-tailed Information Extractioncited by 21
  16. 2023Neurosymbolic AI for Reasoning over Knowledge Graphs: A Surveycited by 21
  17. 2023Debiased Fine-Tuning for Vision-language Models by Prompt Regularizationcited by 20
  18. 2023Causal Unsupervised Semantic Segmentationcited by 18
  19. 2023Learning Distortion Invariant Representation for Image Restoration from A Causality Perspectivecited by 17
  20. 2021The Blessings of Unlabeled Background in Untrimmed Videoscited by 16
  21. 2021Deconfounded Visual Groundingcited by 16
  22. 2023Shift-Robust Molecular Relational Learning with Causal Substructurecited by 15
  23. 2021Improving Weakly-supervised Object Localization via Causal Interventioncited by 14
  24. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  25. 2023Cross-Modal Causal Intervention for Medical Report Generationcited by 14
  26. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  27. 2021Weakly-Supervised Video Object Grounding via Causal Interventioncited by 13
  28. 2022Interventional Multi-Instance Learning with Deconfounded Instance-Level Predictioncited by 13
  29. 2023T2TD: Text-3D Generation Model based on Prior Knowledge Guidancecited by 13
  30. 2021CAM-loss: Towards Learning Spatially Discriminative Feature Representationscited by 12
  31. 2023Causal reasoning in typical computer vision taskscited by 12
  32. 2021Towards Unbiased Visual Emotion Recognition via Causal Interventioncited by 11
  33. 2022Causal Intervention for Subject-Deconfounded Facial Action Unit Recognitioncited by 11
  34. 2024Few-shot Learner Parameterization by Diffusion Time-stepscited by 11
  35. 2021Conterfactual Generative Zero-Shot Semantic Segmentationcited by 10
  36. 2021Confounder Identification-free Causal Visual Feature Learningcited by 10
  37. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10
  38. 2021Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Interventioncited by 9

50 most cited of 112 All 112 (JSON)